The structure of the PAI framework is illustrated below.
The actual ML platform used by PAI is the well-known TensorFlow solution. The neural network structure and the training method are correspondingly developed as Python scripts suitable for TensorFlow and constitute the ML model. The data for supervised learning are prepared in PAI, communication with TensorFlow is implemented via the R console in PMOD.
Learning Set
The Learning Set in PAI consists of references to the training data (i.e. Links to the input series in a PMOD database) and a specification of the preprocessing steps required to bring the data into a format suitable for machine learning. The training data itself consists of data samples. Each data sample consists of an input (one or several images) and its expected segmentation result (one or several segments, in the format of label maps that can be associated with the input images).
Training
Training is performed in TensorFlow using a Learning Set and an ML model. There are different mechanisms available, which will be explained below. Basically, training can be performed locally in PSEG, or delegated to a more powerful infrastructure such as Cloud-Computing.
Training Result
The result of training is a "trained model" - a set of Weights for the layers in neural network, and a Manifest file containing information about the training process. These results are added to the Learning Set, making it ready for use in Prediction (i.e. automated segmentation). As new training data become available, it can be added to the Learning Set and incremental training performed to improve prediction. An export functionality allows transfer of the result to other PMOD installations for prediction (sometimes known as Deployment).
Prediction
Prediction applies the trained model, in PSEG, to a new set of input image data, resulting in a segmentation result. The segments may then be converted to VOIs and used for quantification.
Implementation in PSEG
All PAI functionality is integrated in PSEG. If PAI has been licensed, a + AI indication appears next to PSEG in the main PMOD ToolBox:
Similarly, in PSEG the Segment tab becomes Segment + AI
and the menu button as well:
